Predictive Modeling of Formula 1 Constructor Performance: Discovering the Top Team

Formula One motor-sport is a sport that attracts millions of people worldwide, and performance is influenced by a synergy of drivers, constructors, and engines. The identification of the best-performing constructors is complex because of these interdependencies. While existing studies have focused on isolated factors such as driver performance or engine met-rics, they lack a holistic model that integrates these multiple dimensions. This research fills the gap by creating a holistic framework that evaluates driver performance, engine efficiency, and constructor dynamics over time. We utilize machine learning models such as Random Forest, Decision Tree, Logistic Regression, and LLaMA to predict the top five constructors in Formula 1 races. Of these, the Random Forest model had a higher accuracy level for the ranking of constructors, and hence the output could be of more practical value to stakeholders. This research work, therefore, constitutes an important milestone in further developing the predictive analysis of performance for Formula 1 using various factors that describe performance and advanced machine learning methods.